Research on Superstore Vegetable Pricing and Replenishment Prediction Based on ARIMA Time Series and Particle Swarm Algorithm

Abstract

With the development of digitalization, it is important to provide accurate and reasonable pricing and replenishment strategies for superstores through market demand and data information. In this paper, we first preprocess the relevant data and draw line graphs to compare the correlation between multiple individual items through Spearman correlation analysis. Secondly, Random Forest feature importance analysis is used to explore the relationship between total sales and cost-plus pricing of each vegetable category, and finally, the target data are tested for grade ratio and a gray model is constructed, and model prediction is carried out by using spsspro, and then the particle swarm algorithm is used to derive the optimal pricing strategy. Meanwhile, by updating the pricing regularly and making accurate replenishment decisions, we can better adapt to market fluctuations, obtain better sales opportunities, and maximize the benefits gained by the superstore itself.